Abstract
Multicore platforms are nowadays widely used for audio processing applications, due to the improvement of computational power that they provide. However, some of these systems are not optimized for temporally constrained environments, which often leads to an undesired increase in the latency of the audio signal. This paper presents a real-time multicore audio processing system based on the T-CREST platform. T-CREST is a time-predictable multicore processor for real-time embedded systems. Multiple audio effect tasks have been implemented, which can be connected together in different configurations forming sequential and parallel effect chains, and using a network-on-chip for intercommunication between processors. The evaluation of the system shows that real-time processing of multiple effect configurations is possible, and that the estimation and control of latency ensures real-time behavior.